metadata
library_name: peft
tags:
- parquet
- text-classification
datasets:
- ag_news
metrics:
- accuracy
base_model: moshew/bert-mini-sst2-distilled
model-index:
- name: moshew_bert-mini-sst2-distilled-finetuned-lora-ag_news
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: ag_news
type: ag_news
config: default
split: test
args: default
metrics:
- type: accuracy
value: 0.8921052631578947
name: accuracy
moshew_bert-mini-sst2-distilled-finetuned-lora-ag_news
This model is a fine-tuned version of moshew/bert-mini-sst2-distilled on the ag_news dataset. It achieves the following results on the evaluation set:
- accuracy: 0.8921
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| accuracy | train_loss | epoch |
|---|---|---|
| 0.2483 | None | 0 |
| 0.8812 | 0.4528 | 0 |
| 0.8854 | 0.3449 | 1 |
| 0.8901 | 0.3341 | 2 |
| 0.8921 | 0.3252 | 3 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2